google-health-mcp
Provides read-only access to Fitbit health and fitness data via the Google Health API, including daily summaries, trends, raw records, sleep stages, workouts, GPS routes, profile, goals, devices, and available data types.
Integrates with the Google Health API and Google sign-in to let AI apps query Google Health/Fitbit data such as activity, sleep, heart rate, workouts, profile, and paired devices.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@google-health-mcp How did I sleep last night?"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
google-health-mcp
Unofficial. A community project, not made, endorsed or supported by Google or Fitbit.
Ask Claude, ChatGPT or Grok about your Fitbit or Pixel Watch data: "How did I sleep?", "Steps this month?", "Map my last run". A private, read-only MCP server for the Google Health API that runs free on your own Vercel account. It can only read your data, never change it.
Setup
You need a Fitbit or Pixel Watch synced to the Fitbit / Google Health app, plus free Vercel and GitHub accounts. It takes about 10 minutes.
1. Deploy
Click Deploy with Vercel above. Vercel copies this repo to your GitHub, creates a private storage area for your Google sign-in, and asks for one value:
MCP_HTTP_TOKEN: a random password of 32+ characters (a password manager can generate one, or runopenssl rand -hex 32). Your AI apps use it to reach your data. Save it.
2. Connect Google
Open https://YOUR-APP.vercel.app/auth. The first time, it shows a short checklist for creating a Google sign-in, with direct links and your app's exact redirect URI to copy. Then you add two values in Vercel, redeploy, reload the page and sign in with Google.
You don't need Google's app verification for personal use. On the Google Auth Platform Audience page, click Publish app so it is "In production", because sign-ins in "Testing" expire after 7 days. Google then shows a "Google hasn't verified this app" screen at sign-in; click Advanced → Go to (your app). Unverified apps work for up to 100 users. Full verification of health scopes needs a yearly security assessment, which isn't worth it for your own data. If a form asks for links, use https://YOUR-APP.vercel.app as the home page and https://YOUR-APP.vercel.app/privacy as the privacy policy.
3. Connect your AI app
Add your server address, https://YOUR-APP.vercel.app/mcp, as a connector and click Connect. A page on your own server opens and asks for your MCP_HTTP_TOKEN; type it there and click Allow access. The token never goes into a chat, a URL or the app's settings.
Claude (web, desktop, phone): Settings → Connectors → Add custom connector → paste the address → Connect.
ChatGPT: turn on Developer mode under Settings → Apps & Connectors, create a connector with the address and authentication OAuth.
Grok: grok.com/connectors → New Connector → Custom → paste the address → finish the sign-in that opens.
Claude Code:
claude mcp add --transport http -s user google-health https://YOUR-APP.vercel.app/mcp, then run/mcpin Claude Code and choose Authenticate.
Apps without sign-in support can still send the token directly: header Authorization: Bearer YOUR_TOKEN, or the URL https://YOUR-APP.vercel.app/mcp?key=YOUR_TOKEN (the parameter is key). Your app's home page shows all of this with your address filled in.
Related MCP server: health-mcp
What it can read
Tool | Answers |
| One day at a glance: steps, calories, Active Zone Minutes, resting heart rate, HRV, sleep, workouts |
| Trends per day or week, up to 90 days |
| Hour-by-hour values, such as heart rate during a run |
| Raw records: sleep stages, workouts, weight, SpO2, HRV, ECG |
| A GPS workout's distance, elevation and heart rate. Map points only on request, with 500 m around the start and finish hidden |
| Profile, units, time zone and goals |
| Devices, battery and last sync |
| Every readable data type |
Food and water logs are not available: the Google Health API has no read permission for them yet.
Skill: better answers (optional)
The google-health-insights skill teaches the AI which tool to use for each question, how to read the raw numbers, how to compare them with your own baseline, and when to suggest seeing a doctor. It's a single file, SKILL.md.
Let your AI install it. Paste this into Claude Code or any coding agent:
Install the google-health-insights skill from https://github.com/gokulkrishh/google-health-mcp.
Download https://raw.githubusercontent.com/gokulkrishh/google-health-mcp/main/skills/google-health-insights/SKILL.md
and save it as ~/.claude/skills/google-health-insights/SKILL.md, creating the folder if needed.
Then confirm the file starts with "name: google-health-insights".Or install it yourself:
Claude Code:
mkdir -p ~/.claude/skills/google-health-insights && curl -fsSL https://raw.githubusercontent.com/gokulkrishh/google-health-mcp/main/skills/google-health-insights/SKILL.md -o ~/.claude/skills/google-health-insights/SKILL.mdStart a new session to load it. It's already active when you work inside this repo.
Claude apps (web, desktop, phone): download
SKILL.md, put it in a folder namedgoogle-health-insights, zip that folder, and upload the zip as a custom skill in claude.ai settings.Other AI apps: any app that supports Agent Skills can use the same folder. For apps without skills, paste the contents of
SKILL.mdinto the app's custom instructions or project instructions.
To update the skill later, run the same command or prompt again.
Grok Bot template
grok-bot/TEMPLATE.md sets up a Health Coach Grok Bot in a few copy-pastes: the connector, its standing instructions, three skills (/daily-health-brief, /weekly-health-review, /recovery-check), and routines for a morning brief and a Sunday review.
Troubleshooting
You see | Fix |
| Open |
| Sign in again at |
| The Google client's redirect URI must exactly match the one shown on |
| Open the Fitbit / Google Health phone app with the same Google account and finish setup. |
401 in your AI app | Disconnect and reconnect it, or check the token you typed matches |
No data for today | Open the Fitbit app to sync. Sleep and resting heart rate appear after a night's wear. |
To disconnect Google, remove the app at https://myaccount.google.com/connections. To lock out your AI apps, change MCP_HTTP_TOKEN and redeploy.
Variable | Purpose |
| Required. Secret your AI apps send (32+ characters). |
| Required. Your Google OAuth web client. |
Blob store | Required on Vercel. Created by the Deploy button; keeps your Google sign-in. |
| Only for custom domains: your public |
| Scopes to request. Default |
| Use a refresh token from elsewhere instead of signing in at |
| GPS points this close to a workout's start or finish are never sent to the AI. Default |
Create the Google client as on the
/authchecklist, but use the redirect URIhttp://127.0.0.1:8765/oauth2callback, and save the downloaded JSON as~/.config/google-health-mcp/credentials.json.npm install, thennpm run auth.Add
node /path/to/google-health-mcp/dist/index.js serveas a local MCP server, for exampleclaude mcp add google-health -s user -- node /path/to/google-health-mcp/dist/index.js serve.
Development
npm test builds and runs the unit tests. See AGENTS.md for how the code is organised. MIT licensed.
Available Tools
8 toolsget_daily_rollupDaily totals over a date rangeARead-only
Aggregated values per day (or per N days) for a data type, e.g. steps per day this week, average heart rate per day, weekly distance. Best tool for trends. Max range is 14 days for heart-rate, active-minutes, total-calories and calories-in-heart-rate-zone, 90 days otherwise.
Inputs: endDate (required), dataType (required), startDate (required), windowDays.
get_daily_summaryDaily health summaryARead-only
One-call overview of a single day: steps, distance, calories, active zone minutes, floors, resting heart rate, HRV, sleep that ended that day, and exercise sessions. Start here for questions like 'how did I do today/yesterday'.
Inputs: date.
get_data_pointsRaw data pointsARead-only
Raw records for a data type, newest first: sleep sessions with stages, exercise sessions, weight entries, daily resting heart rate, HRV, SpO2, ECG and so on. Heart-rate and steps produce many points per day, so prefer the rollup tools for those. Pass nextPageToken back as pageToken to read more. For electrocardiogram the API only filters by start, treated as UTC, and end is ignored.
Inputs: dataType (required), end, start, filter, +2 more.
get_exercise_routeWorkout GPS routeARead-only
Route of one GPS workout. By default returns only a summary with no coordinates: distance, duration, elevation gain and heart rate. Set maxPoints only when the user wants to see the route on a map; points near the start and finish are always hidden for privacy, because they usually reveal where the user lives. Get the exercise id from get_data_points with dataType 'exercise'. Workouts recorded without GPS have no route.
Inputs: exercise (required), maxPoints.
get_rollupAggregates over fixed time windowsARead-only
Aggregated values over physical-time windows (e.g. heart rate per 60 minutes during a workout, steps per hour today). Use get_daily_rollup for per-day values.
Inputs: endTime (required), dataType (required), startTime (required), windowMinutes (required).
get_user_infoProfile, settings and identityCRead-only
The user's Google Health identity (user IDs), profile (age, height, stride, etc.) and settings (units, time zone, goals).
Inputs: no named parameters.
list_data_typesList Google Health data typesARead-only
Lists every readable Google Health / Fitbit data type, which tools support it, and the maximum rollup range.
Inputs: no named parameters.
list_paired_devicesPaired devicesARead-only
Devices paired to the account (e.g. Fitbit Air, Pixel Watch), with battery and last sync time when available.
Inputs: no named parameters.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 8 tools
Each tool targets a distinct granularity: daily overview, per-day rollups, time-window rollups, raw points, GPS routes, devices, identity, and a data-type catalog. The only close pair is get_daily_rollup vs get_rollup, but both descriptions explicitly steer the caller ('Use get_daily_rollup for per-day values'), so misselection risk is low.
All names are snake_case and follow a clean list_/get_ verb_noun convention (list_data_types, get_daily_summary, get_exercise_route, etc.). The pattern is predictable and immediately signals read-only intent.
Eight tools is well-scoped for a read-only health data API: one catalog tool, three retrieval granularities, plus routes, devices, and profile. No tool appears redundant or padded.
The surface covers discovery, raw records, aggregation at two resolutions, daily summaries, GPS routes, paired devices, and user profile — essentially full read coverage of the Google Health API. Gaps are minor: no dedicated sleep-session query beyond raw data points, and no write operations (likely by API design).
Maintenance
Related MCP Connectors
Your Garmin, Oura, WHOOP, Hevy and 35 more fitness apps, queryable from your own AI.
Garmin watch data for AI assistants: activities, sleep, HRV, recovery. Never writes to Garmin.
Your Google Health data (Fitbit, Pixel Watch): sleep, HRV, readiness and biological age.
Ask Claude, ChatGPT or Cursor about your Apple Health data: workouts, sleep, food. Read-only.
Related MCP Servers
- AlicenseAqualityDmaintenanceEnables AI assistants to access and analyze Fitbit health data (activity, sleep, heart rate, weight, profile) via natural language through the Fitbit Web API.7MIT
- AlicenseNot gradedqualityBmaintenanceEnables AI agents to query personal health data collected by any wearable or phone fitness app through Android Health Connect or Apple Health, exposing read-only tools for metrics like heart rate, sleep stages, VO2 max, and body composition. It can run locally over USB with nothing stored, or be self-hosted on Cloudflare Workers with D1 to retain history beyond Health Connect's 30-day limit.20 npmMIT
- AlicenseNot gradedqualityBmaintenanceEnables AI assistants to read Fitbit/Google Health data (steps, sleep, heart rate, SpO2, workouts) and log weight, food, water, and exercises via natural language, self-hosted on Cloudflare Workers.5MIT
- AlicenseNot gradedqualityBmaintenanceEnables AI assistants such as Claude, ChatGPT and Gemini to read wearable health data — daily activity, sleep stages, heart rate, SpO2, HRV, workouts, weight and nutrition — through a self-hosted, OAuth-protected Cloudflare Worker endpoint. It also lets users log weight, body fat, water, food, exercises, mood and symptoms by voice or chat, while leaving sensor-recorded data read-only.MIT